Cover Image

Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Hua, Clark, Nicholas, Mitra, Tanushree
Format:	Preprint
Published:	2025
Subjects:	Human-Computer Interaction Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
by: Shen, Hua, et al.
Published: (2024)

Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery
by: Clark, Nicholas, et al.
Published: (2025)

Offscript: Automated Auditing of Instruction Adherence in LLMs
by: Clark, Nicholas, et al.
Published: (2025)

Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment
by: Chen, Jiajun, et al.
Published: (2026)

Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures
by: Shen, Hua, et al.
Published: (2025)

Spontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations
by: Poungpeth, Nalin, et al.
Published: (2026)

The Implications of Open Generative Models in Human-Centered Data Science Work: A Case Study with Fact-Checking Organizations
by: Wolfe, Robert, et al.
Published: (2024)

Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict
by: Chen, Guanyu, et al.
Published: (2026)

Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages
by: Biswas, Shreyan, et al.
Published: (2025)

The Impact and Opportunities of Generative AI in Fact-Checking
by: Wolfe, Robert, et al.
Published: (2024)

Heterogeneous Value Alignment Evaluation for Large Language Models
by: Zhang, Zhaowei, et al.
Published: (2023)

Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation
by: Kaur, Navreet, et al.
Published: (2025)

MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform
by: Jung, Hayoung, et al.
Published: (2025)

Inertia in Moral and Value Judgments of Large Language Models
by: Lee, Bruce W., et al.
Published: (2024)

Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing
by: Hazra, Sanchaita, et al.
Published: (2025)

Algorithmic Behaviors Across Regions: A Geolocation Audit of YouTube Search for COVID-19 Misinformation Between the United States and South Africa
by: Jung, Hayoung, et al.
Published: (2024)

Do We Talk to Robots Like Therapists, and Do They Respond Accordingly? Language Alignment in AI Emotional Support
by: Chiang, Sophie, et al.
Published: (2025)

ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
by: Phutane, Mahika, et al.
Published: (2025)

Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games
by: Yadav, Neemesh, et al.
Published: (2025)

CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions
by: Kim, Tae Soo, et al.
Published: (2025)

Context-Value-Action Architecture for Value-Driven Large Language Model Agents
by: Zhang, TianZe, et al.
Published: (2026)

The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
by: Zhang, Xing, et al.
Published: (2026)

Evaluating AI Alignment in LLMs: Output Analysis of Value Priorities Across 75 Models with Human Benchmarking
by: Lau, Gabriel Rongyang, et al.
Published: (2025)

"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations
by: Dammu, Preetam Prabhu Srikar, et al.
Published: (2024)

Minion: A Technology Probe to Explore How Users Negotiate Harmful Value Conflicts with AI Companions
by: Fan, Xianzhe, et al.
Published: (2024)

Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions
by: Jiang, Yuyang, et al.
Published: (2025)

Democratizing Reward Design for Personal and Representative Value-Alignment
by: Blair, Carter, et al.
Published: (2024)

Position: Towards Bidirectional Human-AI Alignment
by: Shen, Hua, et al.
Published: (2024)

Value Profiles for Encoding Human Variation
by: Sorensen, Taylor, et al.
Published: (2025)

Alignment Drift in Multimodal LLMs: A Two-Phase, Longitudinal Evaluation of Harm Across Eight Model Releases
by: Ford, Casey, et al.
Published: (2026)

Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings
by: Elizabeth, Michelle, et al.
Published: (2024)

Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
by: Greco, Candida M., et al.
Published: (2026)

CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs
by: Liu, Hongtao, et al.
Published: (2025)

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
by: Wu, Zongru, et al.
Published: (2025)

Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
by: Barman, Kristian González, et al.
Published: (2024)

Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMs
by: Jiang, Yi, et al.
Published: (2024)

Mind What You Ask For: Emotional and Rational Faces of Persuasion by Large Language Models
by: Mieleszczenko-Kowszewicz, Wiktoria, et al.
Published: (2025)

Bidirectional Human-AI Alignment in Education for Trustworthy Learning Environments
by: Shen, Hua
Published: (2025)

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents
by: Dongre, Vardhan, et al.
Published: (2024)

MindGuard: Towards Accessible and Sitgma-free Mental Health First Aid via Edge LLM
by: Ji, Sijie, et al.
Published: (2024)